检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Wang, Kunfeng Gou, Chao Wang, Fei-Yue State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Innovation Center for Parallel Vision Qingdao Academy of Intelligent Industries Qingdao266000 China Research Center for Computational Experiments Parallel Systems Technology National University of Defense Technology Changsha410073 China

In this paper, we propose a robust change detection method for intelligent visual surveillance. This method, named M4CD, includes three major steps. Firstly, a sample-based background model that integrates color and texture cues is built and updated over time. Secondly, multiple heterogeneous features (including brightness variation, chromaticity variation, and texture variation) are extracted by comparing the input frame with the background model, and a multi-source learning strategy is designed to online estimate the probability distributions for both foreground and background. The three features are approximately conditionally independent, making multi-source learning feasible. Pixel-wise foreground posteriors are then estimated with Bayes rule. Finally, the Markov random field (MRF) optimization and heuristic post-processing techniques are used sequentially to improve accuracy. In particular, a two-layer MRF model is constructed to represent pixel-based and superpixel-based contextual constraints compactly. Experimental results on the CDnet dataset indicate that M4CD is robust under complex environments and ranks among the top methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

The variability of plant branching and structural properties: data analysis and modeling investigation of winter oilseed rape (Brassica napus) 6

The variability of plant branching and structural properties...

引用

6th International Symposium on Plant Growth Modeling, Simulation, Visualization and Applications (PMA)

作者： Li, Dong Wang, Xiujuan Trask, James C. Lin, Baogang Zhang, Dongqing Minist Agr China Key Lab Informat Traceabil Agr Prod Beijing Peoples R China Zhejiang Acad Agr Sci Inst Digital Agr Hangzhou 310021 Zhejiang Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Qingdao Acad Intelligent Ind Innovat Ctr Parallel Agr Qingdao 266109 Shandong Peoples R China Eweis Labolle Hydrol Associates LLC Davis CA 95616 USA Zhejiang Acad Agr Sci Inst Crop & Nucl Technol Utilizat Hangzhou 310021 Zhejiang Peoples R China

ISBN: (纸本)9781538678152;9781538678169

Winter oilseed rape (Brassica napus) is an important annual crop in many parts of the world. Investigation of structural and developmental branching patterns could lead to improvements in rape breeding and cultivation, and furthermore could lead to improved methods to investigate tree branching patterns. We carried out two-year experiments with two rape plant cultivars for each year. The branches and pods of more than 50 rape plants were counted for each cultivar of each year. Additionally, 3D coordinates of plant structural elements were measured and modeled for four representative rape plants near the maturation phase of growth. For each cultivar, we found the mean number of primary lateral branches per plant was significantly different between different years, but within each year there were no significant differences in the distribution of primary branch number between the two cultivars. Results were different for the total number of all primary and secondary lateral branches per plant and the total number of pods on the main stem per plant. Their frequency distributions changed a lot between different years, cultivars and locations, although the mean values were not significantly different. The 3D measurements showed that azimuth angles of pods and branches were uniformly distributed over 360 degrees, and the inclination angles of pods were centered closely about zero degrees (horizontal). There are challenging aspects of plant structural measurement methodology and structural modeling that have yet to be resolved.

关键词： Branching winter oilseed rape plant modeling

来源：评论

学校读者我要写书评

暂无评论

Transportation by Multiple Mobile Manipulators in Unknown Environments With Obstacles

引用

IEEE systems JOURNAL 2017年第4期11卷 2894-2904页

作者： Jiao, Jile Cao, Zhiqiang Gu, Nong Nahavandi, Saeid Yang, Yuequan Tan, Min Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Deakin Univ Ctr Intelligent Syst Res Waurn Ponds Vic 3217 Australia Yangzhou Univ Coll Informat Engn Yangzhou 225009 Jiangsu Peoples R China

A novel approach to transport a large object by multiple mobile manipulators in unknown environments with obstacles is proposed in this paper. The main moving direction of the system as well as its width and the leading mobile manipulator are first assigned manually or obtained automatically according to the geometric layout of mobile manipulators. Then, three transportation modes, i.e., default mode, shrink mode, and incline mode, are defined based on constraints from the object and mobile manipulators. In default mode, mobile manipulators are distributed around the object to be transported with the initial geometric layout. Mobile manipulators in shrink mode are required to lie inside the boundaries of the object's outlined rectangle, whereas multiple mobile manipulators in incline mode endeavor to hold the object with an inclined angle. On this basis, a decision based on the multiscale passageway is proposed to facilitate the selection of best transportation mode and moving direction. The effectiveness of the approach is verified by simulations and experiments.

关键词： Multiple mobile manipulators multiscale passageway transportation transportation modes unknown environments

来源：评论

学校读者我要写书评

暂无评论

Dynamic Model Based Fuzzy-Impedance Interaction control for Rehabilitation Robots

Dynamic Model Based Fuzzy-Impedance Interaction Control for ...

引用

IEEE International Conference on Robotics and Biomimetics (ROBIO)

作者： Xu, Zihao Wang, Weiqun Hou, Zeng-Guang Lin, Xiaoming Liang, Xu Lanzhou Jiaotong Univ Minist Educ Key Lab Optotechnol & Intelligent Control Lanzhou Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing Peoples R China Lanzhou Jiaotong Univ Mechatron T&R Inst Lanzhou Peoples R China

ISBN: (纸本)9781538637425

During the robot assisted active rehabilitation training, it is very important to adaptively adjust the interaction force between the robot and limbs, online. Aiming at this problem, a fuzzy-impedance control strategy is proposed. First, the difference between the estimated and the measured forces is used to represent the human-robot interaction force. The estimated force is based on rehabilitation robot dynamic model. Then, an adaptive algorithm based on fuzzy logic is presented for adjusting the impedance parameters, including stiffness and damping. Specifically, the interaction force and position errors are used to adjust stiffness, and the interaction force and velocity errors to damping. Finally, the feasibility of the proposed algorithm is verified by the simulation experiment.

关键词： impedance control fuzzy rehabilitation robot dynamic model principle of virtual work

来源：评论

学校读者我要写书评

暂无评论

A new framework of science and technology innovation education for k-12 in Qingdao, China

A new framework of science and technology innovation educati...

引用

2017 ASEE International Forum

作者： Liu, Xiwei Gong, Xiaoyan Wang, Fei-Yue Sun, Rui Gao, Yanqing Zhang, Yu Zhou, Jiehan Deng, Xiaofei State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China Intelligent Education Institution Qingdao Academy of Intelligent Industries China Qingdao Experimental High School China Oregon Institute of Technology United States University of Oulu Finland

来源：评论

学校读者我要写书评

暂无评论

Learning ReLU networks on linearly separable data: Algorithm, optimality, and generalization

arXiv

引用

arXiv 2018年

作者： Wang, Gang Giannakis, Georgios B. Chen, Jie Digital Technology Center Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN55455 United States State Key Lab of Intelligent Control Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Tongji University Shanghai200092 China

Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the underlying data distribution being e.g. Gaussian, or require the network size and/or training size to be sufficiently large. In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data are linearly separable and a hinge loss criterion is adopted. Leveraging the power of random noise perturbation, this paper presents a novel stochastic gradient descent (SGD) algorithm, which can provably train any single-hidden-layer ReLU network to attain global optimality, despite the presence of infinitely many bad local minima, maxima, and saddle points in general. This result is the first of its kind, requiring no assumptions on the data distribution, training/network size, or initialization. Convergence of the resultant iterative algorithm to a global minimum is analyzed by establishing both an upper bound and a lower bound on the number of non-zero updates to be performed. Moreover, generalization guarantees are developed for ReLU networks trained with the novel SGD leveraging classic compression bounds. These guarantees highlight a key difference (at least in the worst case) between reliably learning a ReLU network as well as a leaky ReLU network in terms of sample complexity. Numerical tests using both synthetic data and real images validate the effectiveness of the algorithm and the practical merits of the theory. Copyright © 2018, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

From intelligent control to Smart management of Cyber-Physical-Social systems: A Celebration of 70th Anniversary of Cybernetics by Norbert Wiener

引用

IEEE TRANSACTIONS ON CYBERNETICS 2018年第12期48卷 3278-3279页

作者： Wang, Fei-Yue Filev, Dimitar P. Pedrycz, Witold Li, Hongyi White, Chelsea C., III Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China Ford Motor Co Dearborn MI 48121 USA Univ Alberta Dept Elect & Comp Engn Edmonton AB T6R 2V4 Canada Guangdong Univ Technol Sch Automat Guangzhou 510006 Guangdong Peoples R China Bohai Univ Coll Engn Jinzhou 121013 Peoples R China Georgia Inst Technol H Milton Stewart Sch Ind & Syst Engn Atlanta GA 30332 USA

Inspired by the idealism embodied in Russell and Whitehead’s “Principia Mathematica,” Wiener marched along a different and unique path toward sciences of intelligence and behavior which culminated at “Cybernetics: Or control and Communication in the Animal and the Machine” 70 years ago. Since then, we have witnessed the birth of Cognitive Science, Artificial Intelligence (AI), Computational Intelligence, and many other new research fields and disciplines, all of which have been catalyzed by Cybernetics. The IEEE systems, Man, AND Cybernetics Society and this Transactions on Cybernetics have become the focal point of the broad cybernetics community by promoting the theory, practice, and interdisciplinary aspects of systems science and engineering, human-machine systems, and cybernetics principles. It is a time of celebration and reflection.

关键词： Special issues and sections Cybernetics intelligent control intelligent systems Cyber-physical systems Adaptive systems

来源：评论

学校读者我要写书评

暂无评论

Parallel Transportation management and control System for Subways

引用

IEEE TRANSACTIONS ON intelligent TRANSPORTATION systems 2017年第7期18卷 1974-1979页

作者： Xiong, Gang Shen, Dayong Dong, Xisong Hu, Bin Fan, Dong Zhu, Fenghua Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing Peoples R China Natl Univ Def Technol Coll Informat Syst & Management Changsha Hunan Peoples R China Chinese Acad Sci Cloud Comp Ctr Dongguan Peoples R China Qingdao Acad Intelligent Ind Qingdao Peoples R China Chinese Acad Sci Beijing Engn Res Ctr Intelligent Syst & Technol Inst Automat Beijing Peoples R China

The subway's daily management and control are too complicated to be handled by using traditional methods. Based on the artificial systems, computational experiments, and parallel execution (ACP) approach, the Parallel Transportation management and control System for Subways (PTMS -Subway) is proposed. First, the dynamic status perception and management platform for subways (SPMP-Subway) is constructed, and artificial subway systems (ASS) are designed and constructed, and then they are validated by the real-time data from SPMP-Subway. Then, the design content and construction process of computational experiments platform are performed. Finally, through the interactions of parallel execution system between actual subway and its ASS, a set of practical management and control algorithms can be validated and improved. PTMS-Subway can implement those advanced functions, such as realtime monitoring, warning, forecasting, scheduling optimization, incidence management, and so on, to improve its reliability, efficiency, safety, and service level. SPMP-Subway and PTMS-Subway have been piloted in Subway Lines 1 and 2 in Suzhou, China, and achieved the expected results and benefits successfully.

关键词： Subways ACP approach status perception artificial subway system computational experiments platform parallel execution system

来源：评论

学校读者我要写书评

暂无评论

Task-Space Adaptive Dynamic Modularity control of Free-Floating Space Manipulators 56

Task-Space Adaptive Dynamic Modularity Control of Free-Float...

引用

56th Annual IEEE Conference on Decision and control (CDC)

作者： Wang, Hanlei Cheng, Long Xie, Yongchun Beijing Inst Control Engn Sci & Technol Space Intelligent Control Lab Beijing 100094 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Tianjin Key Lab Micrograv & Hypograv Environm Sim Tianjin 330452 Peoples R China

ISBN: (纸本)9781509028733

In this paper, we investigate the task-space adaptive control problem for free-floating space manipulators with uncertain kinematics and dynamics and with an unmodifiable inner joint control loop. The existence of an unmodifiable inner joint control loop makes most torque-based control algorithms in the literature inapplicable. We propose a dynamic modularity (DM) approach to resolve this problem, and this is hopeful for bridging the potential gap between the advanced control theory for (free-floating) space manipulators and practical engineering applications. Adaptive outer loop controllers are developed and shown to be able to guarantee the convergence of the task-space tracking errors. The performance of the proposed DM approach is shown by a numerical simulation.

关键词： Manipulator dynamics Aerospace electronics Kinematics Space vehicles Jacobian matrices

来源：评论

学校读者我要写书评

暂无评论

An SNR-Adaptive Relaying Algorithm for Multi-Antenna Cooperative Networks

引用

China Communications 2017年第10期14卷 228-236页

作者： Shuangshuang Han Peng Zhang Feijin Shi Fei-Yue Wang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of SciencesBeijing China Qingdao Academy of Intelligent Industries Qingdao Shandong Province China The School of Computer Engineering Weifang University Shandong P. R. China Communications Headquarters Ministry of Foreign Affairs of the People's Republic of China Beijing China Research Center of Computational Experiments and Parallel Systems The National University of Defense Technology Changsha China

Multiple-input multiple-output(MIMO) and cooperative communications have been attracted great attention for the improvements of communication capacity, power consumption, and transmission coverage. The conventional fixed relaying protocols, amplify-and-forward(AF) and decode-and-forward(DF), have their own advantages and disadvantages, i.e. AF performs better than DF for low signal-to-noise ratio(SNR) region, while the reverse is true for high SNR region. Therefore, this paper proposes an SNR-adaptive forward(SAF) relaying scheme obtaining the advantages of both AF and DF. Furthermore, the proposed SAF does not need to switch between AF and DF when SNR changes. The main idea is to adaptively derive the soft information at the cooperative relay nodes based on the information of the received signal and the SNR. Besides, based on the theoretical analysis and the simulation results, it is affirmed that the proposed SAF achieves superior performance than both AF and DF for all SNRs. Moreover, the performance gain would be improved with the increasing number of parallel cooperative relay nodes.

关键词： MIMO SNR SNR-adaptive forward multi-antenna

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：